Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2854 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.5917. Min Act: -0.0000

Data Index: 833059 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.5307. Min Act: -0.0000

Data Index: 1137585 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.4246. Min Act: -0.0000

Data Index: 1352975 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.3943. Min Act: -0.0000

Data Index: 880011 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.3499. Min Act: -0.0000

Data Index: 1291344 (C4 (Web Text))

Max Activating Token Index: 507

Text #5

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.3809. Min Act: -0.0000

Data Index: 282378 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.3488. Min Act: -0.0000

Data Index: 696092 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.3563. Min Act: -0.0000

Data Index: 234029 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.3413. Min Act: -0.0000

Data Index: 886271 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.3394. Min Act: -0.0000

Data Index: 84607 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.3505. Min Act: -0.0000

Data Index: 19968 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.3104. Min Act: -0.0000

Data Index: 336384 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.3015. Min Act: -0.0000

Data Index: 628471 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.2956. Min Act: -0.0000

Data Index: 189500 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.2644. Min Act: -0.0000

Data Index: 1195902 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.3003. Min Act: -0.0000

Data Index: 154732 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.3018. Min Act: -0.0000

Data Index: 509986 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.2934. Min Act: -0.0000

Data Index: 63845 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.2912. Min Act: -0.0000

Data Index: 1203196 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 0.5917. Min Range: -0.5917

Max Act: 0.2788. Min Act: -0.0000

Data Index: 72300 (C4 (Web Text))

Max Activating Token Index: 72